© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51028
    Prev
    Next
    INDEX
    Explanations

    end of code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĢæĽ²
    -0.08
    /fw
    -0.08
    egis
    -0.07
    èĭ
    -0.07
    ÙģÙĪ
    -0.07
    mata
    -0.07
    ä¸Ģå¼łå¼ł
    -0.07
    ÙĨÛĮÙĨ
    -0.07
    unci
    -0.07
    è¾īæĺł
    -0.07
    POSITIVE LOGITS
    _vendor
    0.07
    asar
    0.07
    atie
    0.07
     supposedly
    0.06
     allegedly
    0.06
    _eof
    0.06
    æĬķåħ¥åĪ°
    0.06
    æ³ĽæĮĩ
    0.06
     Quiet
    0.06
    ë§ĪìŀIJ
    0.06
    Activations Density 0.014%

    No Known Activations